发表机构
Chung-Ang University; Korea Electronics Technology Institute (KETI)（中央大学; 韩国电子技术研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对头部虚拟形象，提出URHead统一表示法，通过UV空间统一及联合优化，让网格与高斯方法互补，保持参数可控性与特定主体细节，在重建质量和动画一致性上超越现有方法。
AI 中文摘要
我们提出了URHead，这是一种用于高保真且可动画化头部虚拟形象的统一表示，它从根本上重新定义了网格-高斯积分。基于网格的方法能提供精确几何控制但缺乏逼真细节，基于高斯的方法能实现逼真效果但结构一致性差，现有混合解决方案未能充分利用其互补优势。我们的关键贡献是UV空间统一，两种表示共享通用UV参数化。通过自适应高斯采样进行联合优化，该方法自动学习分离并为每个组件分配适当角色。URHead保持完全参数可控性，同时保留特定主体细节，在重建质量和动画一致性方面优于现有最先进方法。
英文摘要
We present URHead, a unified representation for high-fidelity and animatable head avatars that fundamentally redefines mesh-Gaussian integration. While mesh-based methods offer precise geometric control but lack photorealistic detail, and Gaussian-based approaches achieve photorealism but suffer from poor structural consistency, existing hybrid solutions fail to fully leverage their complementary strengths. Our key contribution is a UV-space unification where both representations share a common UV parameterization. Through joint optimization with adaptive gaussian sampling, our method automatically learns to disentangle and allocate appropriate roles to each component. URHead maintains full parametric controllability while preserving subject-specific details, and outperforms existing state-of-the-art methods in reconstruction quality and animation consistency.
CommentsProject page/code: https://lseonghak.github.io/website/project/urhead/, Accepted to ECCV 2026
